ableton-mcp

Overview Schema Source Related Servers Discussions Admin

search_local_splice_samples

Read-onlyIdempotent

Search local Splice audio files by filename, folder, private tags, or favorite status to find matches; filter metadata before pagination without cloud search.

Instructions

Search existing local Splice audio files by filename/folder, private favorite state and/or private tags. Query is optional when a metadata filter is supplied. Filtering happens before pagination; visited and truncated report an incomplete bounded scan. Private metadata is not a native Splice collection; no cloud search, license verification, download, or sync.

Input Schema

Name	Required	Description
`tags`	No	Require every supplied tag.
`limit`	No
`query`	No	Optional case-insensitive audio filename or relative-path query; required without metadata filters.
`offset`	No	Zero-based match offset for deterministic pagination; defaults to zero.
`favorite`	No	Optional private favorite state filter.
`maxDepth`	No
`rootPath`	Yes	Absolute local Splice asset directory.
`maxVisited`	No	Maximum directory entries to inspect; defaults to 50000. A truncated result is incomplete.
`includeMetadata`	No	Include private MCP tags and favorites for matching local files.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.1Oct 23, 2026

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "limitation": {
+        "type": "string"
+      },
+      "maxVisited": {
+        "type": "integer"
+      },
+      "nextOffset": {
+        "anyOf": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "offset": {
+        "type": "integer"
+      },
+      "query": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "rootPath": {
+        "type": "string"
+      },
+      "samples": {
+        "items": {
+          "properties": {
+            "relativePath": {
+              "type": "string"
+            },
+            "sourcePath": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "relativePath",
+            "sourcePath"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "scope": {
+        "const": "local_files_only"
+      },
+      "truncated": {
+        "type": "boolean"
+      },
+      "visited": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "rootPath",
+      "query",
+      "scope",
+      "offset",
+      "visited",
+      "maxVisited",
+      "truncated",
+      "nextOffset",
+      "samples",
+      "limitation"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "outcome": {
+            "enum": [
+              "unknown",
+              "not_executed"
+            ]
+          }
+        },
+        "required": [
+          "message",
+          "outcome"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

Changed1 schema field changedv0.3.0Oct 19, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

Changed7 schema fields changedv0.2.0Sep 30, 2026

addedInput schema / properties / favorite

Added value: +{
+  "description": "Optional private favorite state filter.",
+  "type": "boolean"
+}

addedInput schema / properties / includeMetadata

Added value: +{
+  "description": "Include private MCP tags and favorites for matching local files.",
+  "type": "boolean"
+}

addedInput schema / properties / maxVisited

Added value: +{
+  "description": "Maximum directory entries to inspect; defaults to 50000. A truncated result is incomplete.",
+  "maximum": 50000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "Zero-based match offset for deterministic pagination; defaults to zero.",
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / query / description

Previous value: -"Case-insensitive audio filename query."New value: +"Optional case-insensitive audio filename or relative-path query; required without metadata filters."

addedInput schema / properties / tags

Added value: +{
+  "description": "Require every supplied tag.",
+  "items": {
+    "description": "Required private user tag.",
+    "type": "string"
+  },
+  "type": "array"
+}

changedInput schema / required

Previous value: -[
-  "rootPath",
-  "query"
-]New value: +[
+  "rootPath"
+]

First observedv0.1.0Sep 23, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: filtering happens before pagination, visited/truncated signal an incomplete bounded scan, and private metadata is not a native Splice collection. It does not cover error conditions or permission requirements, keeping it at 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tightly packed sentences with the core purpose front-loaded and zero filler. The clause 'visited and truncated report an incomplete bounded scan' is dense to the point of being slightly telegraphic, but every sentence carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return shape, and it correctly focuses on scope limits, pagination ordering, and truncation semantics for a 9-parameter tool with a required rootPath. Adequate; only the lack of sibling routing and error behavior keeps it below a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 78%, so the schema carries most parameter meaning. The description still adds value by mapping its stated filter dimensions (filename/folder, favorite, tags) onto query/favorite/tags and by explaining the conditional requirement that query is optional only when a metadata filter is present — a rule the schema only partially states on the query param.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource (local Splice audio files) plus the exact filter dimensions: filename/folder, favorite state, tags. This is clearly distinct from siblings like browse_local_splice_directory (directory listing) or search_browser_items (Live browser), so an agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete precondition ('Query is optional when a metadata filter is supplied') and explicit exclusions ('no cloud search, license verification, download, or sync'), which tells the agent when this tool is the wrong choice. It stops short of naming the sibling tool to use instead for directory browsing or cloud-side search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server